linux/net/ipv4/tcp_minisocks.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Implementation of the Transmission Control Protocol(TCP).
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <[email protected]>
 *		Mark Evans, <[email protected]>
 *		Corey Minyard <[email protected]>
 *		Florian La Roche, <[email protected]>
 *		Charles Hedrick, <[email protected]>
 *		Linus Torvalds, <[email protected]>
 *		Alan Cox, <[email protected]>
 *		Matthew Dillon, <[email protected]>
 *		Arnt Gulbrandsen, <[email protected]>
 *		Jorge Cwik, <[email protected]>
 */

#include <net/tcp.h>
#include <net/xfrm.h>
#include <net/busy_poll.h>
#include <net/rstreason.h>

static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
{ … }

static enum tcp_tw_status
tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw,
				  const struct sk_buff *skb, int mib_idx)
{ … }

static void twsk_rcv_nxt_update(struct tcp_timewait_sock *tcptw, u32 seq)
{ … }

/*
 * * Main purpose of TIME-WAIT state is to close connection gracefully,
 *   when one of ends sits in LAST-ACK or CLOSING retransmitting FIN
 *   (and, probably, tail of data) and one or more our ACKs are lost.
 * * What is TIME-WAIT timeout? It is associated with maximal packet
 *   lifetime in the internet, which results in wrong conclusion, that
 *   it is set to catch "old duplicate segments" wandering out of their path.
 *   It is not quite correct. This timeout is calculated so that it exceeds
 *   maximal retransmission timeout enough to allow to lose one (or more)
 *   segments sent by peer and our ACKs. This time may be calculated from RTO.
 * * When TIME-WAIT socket receives RST, it means that another end
 *   finally closed and we are allowed to kill TIME-WAIT too.
 * * Second purpose of TIME-WAIT is catching old duplicate segments.
 *   Well, certainly it is pure paranoia, but if we load TIME-WAIT
 *   with this semantics, we MUST NOT kill TIME-WAIT state with RSTs.
 * * If we invented some more clever way to catch duplicates
 *   (f.e. based on PAWS), we could truncate TIME-WAIT to several RTOs.
 *
 * The algorithm below is based on FORMAL INTERPRETATION of RFCs.
 * When you compare it to RFCs, please, read section SEGMENT ARRIVES
 * from the very beginning.
 *
 * NOTE. With recycling (and later with fin-wait-2) TW bucket
 * is _not_ stateless. It means, that strictly speaking we must
 * spinlock it. I do not want! Well, probability of misbehaviour
 * is ridiculously low and, seems, we could use some mb() tricks
 * to avoid misread sequence numbers, states etc.  --ANK
 *
 * We don't need to initialize tmp_out.sack_ok as we don't use the results
 */
enum tcp_tw_status
tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
			   const struct tcphdr *th, u32 *tw_isn)
{ … }
EXPORT_SYMBOL(…);

static void tcp_time_wait_init(struct sock *sk, struct tcp_timewait_sock *tcptw)
{ … }

/*
 * Move a socket to time-wait or dead fin-wait-2 state.
 */
void tcp_time_wait(struct sock *sk, int state, int timeo)
{ … }
EXPORT_SYMBOL(…);

#ifdef CONFIG_TCP_MD5SIG
static void tcp_md5_twsk_free_rcu(struct rcu_head *head)
{ … }
#endif

void tcp_twsk_destructor(struct sock *sk)
{ … }
EXPORT_SYMBOL_GPL(…);

void tcp_twsk_purge(struct list_head *net_exit_list)
{ … }

/* Warning : This function is called without sk_listener being locked.
 * Be sure to read socket fields once, as their value could change under us.
 */
void tcp_openreq_init_rwin(struct request_sock *req,
			   const struct sock *sk_listener,
			   const struct dst_entry *dst)
{ … }
EXPORT_SYMBOL(…);

static void tcp_ecn_openreq_child(struct tcp_sock *tp,
				  const struct request_sock *req)
{ … }

void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
{ … }
EXPORT_SYMBOL_GPL(…);

static void smc_check_reset_syn_req(const struct tcp_sock *oldtp,
				    struct request_sock *req,
				    struct tcp_sock *newtp)
{ … }

/* This is not only more efficient than what we used to do, it eliminates
 * a lot of code duplication between IPv4/IPv6 SYN recv processing. -DaveM
 *
 * Actually, we could lots of memory writes here. tp of listening
 * socket contains all necessary default parameters.
 */
struct sock *tcp_create_openreq_child(const struct sock *sk,
				      struct request_sock *req,
				      struct sk_buff *skb)
{ … }
EXPORT_SYMBOL(…);

/*
 * Process an incoming packet for SYN_RECV sockets represented as a
 * request_sock. Normally sk is the listener socket but for TFO it
 * points to the child socket.
 *
 * XXX (TFO) - The current impl contains a special check for ack
 * validation and inside tcp_v4_reqsk_send_ack(). Can we do better?
 *
 * We don't need to initialize tmp_opt.sack_ok as we don't use the results
 *
 * Note: If @fastopen is true, this can be called from process context.
 *       Otherwise, this is from BH context.
 */

struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
			   struct request_sock *req,
			   bool fastopen, bool *req_stolen)
{ … }
EXPORT_SYMBOL(…);

/*
 * Queue segment on the new socket if the new socket is active,
 * otherwise we just shortcircuit this and continue with
 * the new socket.
 *
 * For the vast majority of cases child->sk_state will be TCP_SYN_RECV
 * when entering. But other states are possible due to a race condition
 * where after __inet_lookup_established() fails but before the listener
 * locked is obtained, other packets cause the same connection to
 * be created.
 */

enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child,
				       struct sk_buff *skb)
	__releases(&((child)->sk_lock.slock))
{ … }
EXPORT_SYMBOL(…);